Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of international agreements or political actions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and commas in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isy
    -0.66
    ocl
    -0.60
    lymp
    -0.59
    iquette
    -0.59
    odes
    -0.58
    ocy
    -0.58
    aea
    -0.58
    iltr
    -0.57
    EngineDebug
    -0.56
    =#
    -0.55
    POSITIVE LOGITS
     which
    1.17
     aka
    1.16
    which
    1.10
     nicknamed
    0.96
     whose
    0.93
     whereby
    0.91
     wherein
    0.89
    whose
    0.88
    channelAvailability
    0.87
     pictured
    0.87
    Act Density 0.421%

    No Known Activations